Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Ming-Hsuan Yang

Ming-Hsuan Yang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Vision×5NLP×2AI×2

Frequent co-authors

Jixuan He2×
Xueting Li2×
Chieh Hubert Lin2×
Fangzhou Lin2×
Peiran Li2×
Lingyu Xu2×

Research Timeline

2026
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning and structural control.

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning and structural control.

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, achieving significant gains over unconstrained tool use.

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, achieving significant gains over unconstrained tool use.

Learning to Correct Geometry in Generated Videos

This paper proposes a post-hoc video-to-video model called Video Geometry Corrector (VGC) to improve geometric consistency in generated videos.

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentOct 16, 2026

Learning to Correct Geometry in Generated Videos

Weijie Lyu, Tiancheng Shen, Jason Li, Yujing Wang +4 more

This paper proposes a post-hoc video-to-video model called Video Geometry Corrector (VGC) to improve geometric consistency in generated videos.

View →
cs.CVcs.CLRecentMay 31, 2026

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning

Jixuan He, Xueting Li, Chieh Hubert Lin, Ming-Hsuan Yang

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

View →
cs.CVcs.CLRecentMay 31, 2026

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning

Jixuan He, Xueting Li, Chieh Hubert Lin, Ming-Hsuan Yang

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

View →
cs.CVcs.AIRecentMay 30, 2026

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

Fangzhou Lin, Peiran Li, Lingyu Xu, Wenjing Chen +11 more

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…

View →
cs.CVcs.AIRecentMay 30, 2026

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

Fangzhou Lin, Peiran Li, Lingyu Xu, Wenjing Chen +11 more

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…

View →